© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21399
    Prev
    Next
    INDEX
    Explanations

    impressive or impress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strange
    -0.13
    Strange
    -0.11
     ign
    -0.11
    ainties
    -0.10
     confusing
    -0.10
     fame
    -0.10
     puzzled
    -0.10
     strange
    -0.10
     Fame
    -0.09
     popularity
    -0.09
    POSITIVE LOGITS
     impressive
    0.58
     impressed
    0.57
     impress
    0.54
     impression
    0.45
     impres
    0.41
    Imp
    0.39
     Imp
    0.39
     Impress
    0.34
     impressions
    0.33
     ấn
    0.30
    Activations Density 0.202%

    No Known Activations